Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials on organic and inorganic compounds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917281376763904 |
|---|---|
| author | Laskaris, G. Morozov, D. Tarpanov, D. Seth, A. Procelewska, J. Gautam, G. Sai Sagingalieva, A. Brasher, R. Melnikov, A. |
| author_facet | Laskaris, G. Morozov, D. Tarpanov, D. Seth, A. Procelewska, J. Gautam, G. Sai Sagingalieva, A. Brasher, R. Melnikov, A. |
| contents | Allegro is a machine learning interatomic potential (MLIP) model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason we apply multi-objective hyperparameter optimization to the two objectives. Additionally, we experiment with modified architectures by making variants of Allegro some by adding strictly classical multi-layer perceptron (MLP) layers and some by adding quantum-classical hybrid layers. We compare the results from QM9, rMD17-aspirin, rMD17-benzene and our own proprietary dataset consisting of copper and lithium atoms. As results, we have a list of variants that surpass the Allegro in accuracy and also results which demonstrate the trade-off with inference times. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16908 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials on organic and inorganic compounds Laskaris, G. Morozov, D. Tarpanov, D. Seth, A. Procelewska, J. Gautam, G. Sai Sagingalieva, A. Brasher, R. Melnikov, A. Materials Science Machine Learning Quantum Physics Allegro is a machine learning interatomic potential (MLIP) model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason we apply multi-objective hyperparameter optimization to the two objectives. Additionally, we experiment with modified architectures by making variants of Allegro some by adding strictly classical multi-layer perceptron (MLP) layers and some by adding quantum-classical hybrid layers. We compare the results from QM9, rMD17-aspirin, rMD17-benzene and our own proprietary dataset consisting of copper and lithium atoms. As results, we have a list of variants that surpass the Allegro in accuracy and also results which demonstrate the trade-off with inference times. |
| title | Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials on organic and inorganic compounds |
| topic | Materials Science Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2602.16908 |